On-line temperature monitoring system for heated body of heat treatment furnace

Abstract

The invention discloses an on-line temperature monitoring system for a heated body of a heat treatment furnace, which belongs to the technical field of heat treatment furnaces and specifically comprises an infrared imaging module for generating a thermal image of a temperature field in the heat treatment furnace based on an infrared temperature measurement technology; the steel pipe identification module is used for preprocessing the thermal imaging image, performing edge detection on the preprocessed thermal imaging image, identifying a boundary line between each steel pipe area and the surrounding area, and obtaining the steel pipe area in the thermal imaging image; the temperature analysis module is used for obtaining temperature data of the steel pipe area, the temperature data comprise the average temperature, the highest point temperature and the lowest point temperature, and whether steel pipe heat treatment runs normally or not is judged according to the temperature data; and the period adjustment module is used for setting a monitoring period and a standard duration, counting the temperature data every n monitoring periods, calculating a period adjustment coefficient according to the temperature data, and calculating the duration of the next n monitoring periods according to the period adjustment coefficient.

Description

Technical Field

[0001] The invention relates to the technical field of heat treatment furnaces, and in particular to an online monitoring system for the temperature of a heated body in a heat treatment furnace. Background Art

[0002] In the heat treatment process, accurate monitoring of the temperature of the heated object, such as steel pipes, is an important part of ensuring product quality and process stability. Traditional temperature monitoring methods mainly rely on thermocouples or other contact temperature sensors. Although these methods can provide local temperature information, contact sensors such as thermocouples can only measure single-point temperature and it is difficult to fully reflect the distribution of the temperature field in the heat treatment furnace. Contact sensors are easily affected by the complex atmosphere in the heat treatment furnace under high temperature conditions, resulting in measurement errors. In addition, the installation and maintenance of sensors may also interfere with the production process.

[0003] With the development of infrared imaging technology and image processing technology, non-contact temperature monitoring methods have gradually attracted attention. Infrared imaging technology can generate temperature distribution images by detecting infrared radiation on the surface of an object, providing more comprehensive temperature information for the heat treatment process.

[0004] However, when the prior art applies infrared imaging to the temperature monitoring of the heat treatment furnace, it is still difficult to accurately identify the boundary of the heated steel pipe when performing temperature analysis on the heated body, resulting in limited accuracy of the temperature data. In addition, the prior art often adopts a fixed monitoring cycle and cannot dynamically adjust the monitoring frequency according to the actual temperature changes of the heat treatment process, which may lead to the omission of important information or waste of resources. Based on this, the present invention provides an efficient and accurate online monitoring system for the temperature of the heated body of the heat treatment furnace. Summary of the invention

[0005] The purpose of the present invention is to provide an online monitoring system for the temperature of a heated body in a heat treatment furnace to solve the following technical problems: When infrared imaging is used for temperature monitoring of heat treatment furnaces, it is difficult to accurately identify the boundaries of the heated steel pipe, resulting in limited accuracy of temperature data. In addition, existing technologies often use a fixed monitoring cycle and cannot dynamically adjust the monitoring frequency according to the actual temperature changes during the heat treatment process, which may lead to the omission of important information or waste of resources.

[0006] The purpose of the present invention can be achieved through the following technical solutions: An online monitoring system for the temperature of a heated body in a heat treatment furnace, comprising: Infrared imaging module, used to generate thermal imaging of the temperature field in the heat treatment furnace based on infrared temperature measurement technology; A steel pipe identification module is used to preprocess the thermal image, perform edge detection on the preprocessed thermal image, identify the boundary line between each steel pipe area and the surrounding area, and obtain the steel pipe area in the thermal image; The temperature analysis module is used to obtain the temperature data of the steel pipe area, the temperature data includes the average temperature, the highest point temperature and the lowest point temperature, and judge whether the heat treatment of the steel pipe is running normally according to the temperature data; The cycle adjustment module is used to set the monitoring cycle, the standard duration of the monitoring cycle is T, the temperature data is counted every n monitoring cycles, the cycle adjustment coefficient is calculated based on the temperature data, and the duration of the next n monitoring cycles is calculated based on the cycle adjustment coefficient.

[0007] As a further solution of the present invention: the process of the infrared imaging module generating a thermal imaging image of the temperature field in the heat treatment furnace based on the infrared temperature measurement technology is as follows: The infrared imaging module is based on an infrared detector array composed of several infrared detectors. The infrared detector array receives infrared radiation energy in the heat treatment furnace, converts infrared radiation at different positions in the furnace into electrical signals, amplifies and filters the electrical signals through a built-in signal processing circuit, and converts analog-to-digital signals into digital signals. These digital signals are calculated based on a preset algorithm to obtain the temperature values ​​corresponding to each position in the heat treatment furnace, and generate a thermal imaging map of the temperature field in the heat treatment furnace through visualization processing.

[0008] As a further solution of the present invention: the process of preprocessing the thermal image by the steel pipe identification module is as follows: The thermal image is converted into a grayscale image. Based on the 3×3 template of the Laplace operator, each pixel in the grayscale image is multiplied and summed with the adjacent 3×3 pixels point by point. The summed grayscale value result is marked as the new grayscale value of the middle pixel, and all the pixels in the thermal image are updated respectively.

[0009] As a further solution of the present invention: the steel pipe identification module performs edge detection on the pre-processed thermal imaging image, and the process of identifying the boundary line between each steel pipe area and the surrounding area is as follows: Get the placement direction of the steel pipe, start from the edge of the grayscale image parallel to the steel pipe, select a column of pixels in turn, calculate the mean grayscale value of the selected column of pixels, and perform difference calculation with the mean grayscale value of the pixels in the next column. When the difference is greater than the preset threshold, mark the lower mean between the two columns of pixels as a pending boundary line and define it as the starting line. Traverse the grayscale image and mark the last pending boundary line as the end line. When the number of pending boundary lines is greater than 2, mark the pending boundary lines within the set range near the starting line as the starting line group. The pending boundary lines within the set range near the end line are marked as the end line group, and each pending boundary line in the start line group and the end line group is traversed respectively. For each pending boundary line, starting from one end of the pending boundary line, the grayscale value of the pixel point is compared with the grayscale value of the next pixel point in turn, and the smaller pixel point between the two pixel points whose difference is greater than the preset threshold is marked as an edge point, and all edge points in the start line group and the end line group are connected respectively, and the connected edge points are linearly fitted, and the fitted straight line is marked as the boundary line of the steel pipe area.

[0010] As a further solution of the present invention: when the number of the pending boundary lines is equal to 2, they are directly marked as the steel pipe area boundary lines.

[0011] As a further solution of the present invention: when the deviation between the slope of any fitted straight line and the slope of the set direction is greater than the set deviation, an abnormal prompt is issued.

[0012] As a further solution of the present invention: the process of judging whether the heat treatment of the steel pipe is operating normally in the temperature analysis module according to the temperature data is to respectively calculate the difference Dmax and the difference Dmax between the highest point temperature and the lowest point temperature and the average temperature. When any difference is greater than the set difference, it is judged that the heat treatment furnace is operating abnormally.

[0013] As a further solution of the present invention, the cycle adjustment module counts the temperature data every n monitoring cycles, calculates the cycle adjustment coefficient according to the temperature data, and calculates the duration of the next n monitoring cycles according to the cycle adjustment coefficient as follows: During the constant temperature heat treatment of the steel pipe, the average temperature Ta, difference Dmax, and difference Dmax of the steel pipe area are counted every n monitoring cycles, and the proportions K1, K2, and K3 of the average temperature Ta, difference Dmax, and difference Dmax exceeding the corresponding set interval are counted respectively; The weighted moving average value T0 of n monitoring cycles is statistically calculated, and T0 is added to the average temperature Ta sequence. A point diagram of the average temperature changing with the number of monitoring times is drawn according to the average temperature Ta sequence, and the slope k of the line segment between every two adjacent points is obtained. The calculation formula of the cycle adjustment coefficient C is: ; Among them, ki represents the slope of the i-th line segment in the inflection point graph, kmax represents the maximum value of the slope, kmin represents the minimum value of the slope, and c represents the compensation coefficient, which is used to prevent the adjustment coefficient value from being 0 or meaningless; Then the duration of the next n monitoring cycles is Tnew=T / C.

[0014] As a further solution of the present invention: the specific process of calculating the weighted moving average value T0 of n monitoring cycles is as follows: Get the average temperature XT of the last n monitoring cycles, and assign a corresponding weight to each average temperature XT. The weight increases gradually according to the time sequence. The calculation formula of the weighted moving average value T0 is: ; Among them, XTi represents the i-th average temperature XT, and ωi represents the weight of the i-th average temperature XT.

[0015] Beneficial effects of the present invention: The present invention generates a thermal image of the temperature field in the heat treatment furnace based on infrared temperature measurement technology through an infrared imaging module, which can show the temperature distribution in the furnace in real time and intuitively. The steel pipe recognition module performs preprocessing and edge detection on the thermal image, and can accurately identify the boundary line between each steel pipe area and the surrounding area, and accurately obtain the steel pipe area in the thermal image. The preprocessing process uses the Laplace operator to enhance the image, effectively highlighting the edge information; the edge detection method can adapt to steel pipes in different placement directions and accurately mark the boundary line through a series of detailed calculations and judgments. This precise steel pipe recognition function provides a guarantee for the subsequent accurate acquisition of temperature data of the steel pipe area, ensuring the accuracy of temperature analysis. Dynamic cycle adjustment: The cycle adjustment module can dynamically adjust the monitoring cycle according to the temperature data during the heat treatment of the steel pipe. The temperature data is counted every n monitoring cycles, and the cycle adjustment coefficient is calculated to obtain the duration of the next n monitoring cycles. This dynamic adjustment mechanism fully considers the temperature changes during the heat treatment process. When the temperature fluctuates greatly or shows abnormal trends, the monitoring period can be shortened and temperature monitoring can be strengthened. When the temperature is relatively stable, the monitoring period can be appropriately extended to improve monitoring efficiency. At the same time, it can also reasonably allocate monitoring resources and reduce system operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] Figure 1 It is a module schematic diagram of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 As shown, the present invention is an online monitoring system for the temperature of a heated body in a heat treatment furnace, comprising: Infrared imaging module, the infrared imaging module is a core component based on infrared temperature measurement technology, which is used to generate thermal imaging images of the temperature field in the heat treatment furnace. The module consists of an array of several infrared detectors that can receive infrared radiation energy at different positions in the heat treatment furnace. When the surface temperature of an object is higher than absolute zero, it will emit infrared radiation. The infrared detector captures this radiation energy and converts it into electrical signals. Subsequently, these electrical signals are amplified and filtered by the built-in signal processing circuit to reduce noise and interference. The preliminarily processed signals are then converted into digital signals by an analog-to-digital converter (ADC).

[0020] Based on the preset algorithm, the system calculates these digital signals to obtain the temperature values ​​corresponding to each position in the heat treatment furnace. In order to present these temperature data in an intuitive way, the system will perform visualization processing to generate a thermal image of the temperature field in the heat treatment furnace. This thermal image can not only clearly display the temperature distribution, but also mark different temperature areas with different colors through pseudo-color coding technology, so that operators can quickly identify abnormal temperature areas. In addition, the infrared imaging module also has the characteristics of high sensitivity and high resolution, which can detect tiny temperature changes and is suitable for complex industrial environments.

[0021] Steel pipe identification module is the key part of this system for processing thermal images and identifying steel pipe areas. Its core function is to pre-process thermal images to enhance the edge information of the image, which is convenient for subsequent steel pipe area identification and boundary extraction. The specific process of pre-processing is as follows: First, the thermal image is converted into a grayscale image. This process is achieved by simplifying the color information of each pixel in the color image into a grayscale value, thereby reducing the amount of data and highlighting the brightness information of the image. The grayscale image retains the basic characteristics of the temperature distribution while reducing the computational complexity, providing a basis for subsequent edge detection.

[0022] Next, the module uses a 3×3 template based on the Laplacian operator to process the grayscale image. The Laplacian operator is a commonly used edge detection operator that can effectively detect areas where the grayscale value changes in the image, thereby highlighting the contours and boundaries of the object. In the specific operation, the 3×3 template of the Laplacian operator is convolved with each pixel in the grayscale image and its adjacent 3×3 pixels. The convolution operation process is to multiply each value in the template with the corresponding pixel grayscale value point by point, and sum the product results. The summed grayscale value result is marked as the new grayscale value of the middle pixel, thereby completing the update of the pixel.

[0023] In this way, the module updates all the pixels in the thermal image in sequence. After the Laplace operator is processed, the edge information of the image will be significantly enhanced, while the background noise will be suppressed. This enhanced grayscale image can clearly show the boundary between the steel pipe and the surrounding environment, providing a high-quality image foundation for subsequent steel pipe area recognition and boundary extraction.

[0024] In the pre-processed thermal image, the steel pipe recognition module uses a series of complex edge detection algorithms to identify the boundary between each steel pipe area and the surrounding area, thereby accurately extracting the steel pipe area in the thermal image. The specific process is as follows: First, the system obtains the orientation of the steel pipe in the heat treatment furnace. This is achieved by analyzing the overall layout of the grayscale image or pre-set process parameters. After determining the orientation, the system selects a column of pixels in the grayscale image, starting from the edge parallel to the steel pipe. For each column of pixels, the system calculates the mean of its grayscale value and performs a difference calculation with the mean of the grayscale value of the next column of pixels. This process is designed to detect sudden changes in grayscale values ​​and thus identify the boundary between the steel pipe and the surrounding environment.

[0025] When the difference between the grayscale values ​​of two adjacent columns of pixels is greater than a preset threshold, the system marks the column with the lower mean value between the two columns of pixels as the "pending boundary line" and defines it as the "starting line". Subsequently, the system continues to traverse the grayscale image column by column until the last column of pending boundary lines is found and marked as the "ending line".

[0026] If the number of pending boundary lines is greater than 2 during the traversal process, the system will further process these pending boundary lines. Specifically, the system marks the pending boundary lines within the set range near the start line as the "starting line group" and marks the pending boundary lines within the set range near the end line as the "ending line group". This set range is predetermined based on the size and placement density of the steel pipes to ensure that different steel pipe areas can be accurately distinguished.

[0027] Next, the system traverses each pending boundary line in the start line group and the end line group point by point. For each pending boundary line, the system starts from one end and compares the grayscale values ​​of adjacent pixels in turn. When the grayscale value difference between two adjacent pixels is greater than the preset threshold, the system marks the pixel with the smaller grayscale value between the two pixels as an "edge point". This process further refines the position of the boundary by detecting local changes in grayscale values.

[0028] Then, the system connects all edge points in the start line group and the end line group, and performs linear fitting on the connected edge points. The fitted straight line is marked as the boundary line of the steel pipe area. In this way, the system can accurately depict the outline of the steel pipe, thereby realizing the recognition and extraction of the steel pipe area.

[0029] In some cases, the number of pending boundary lines may be only 2. In this case, the system directly marks these two pending edge lines as the boundary lines of the steel pipe without further linear fitting processing.

[0030] In addition, the system also has an abnormality detection function. When the deviation between the slope of the fitted straight line and the slope of the preset steel pipe placement direction is greater than the set threshold, the system will issue an abnormality prompt. This function can promptly detect the position deviation or other abnormal conditions of the steel pipe during the heat treatment process, thereby ensuring the stability of the heat treatment process and product quality.

[0031] Temperature analysis module, the temperature analysis module is the core part of the heat treatment furnace temperature monitoring system. Its main function is to obtain the temperature data of the steel pipe area, and to determine whether the operation status of the heat treatment furnace is normal by calculating and analyzing these data. Specifically, the module can extract the average temperature, the highest point temperature and the lowest point temperature of the steel pipe area. Based on these temperature data, the module calculates the difference between the highest point temperature and the average temperature (denoted as Dmax) and the difference between the lowest point temperature and the average temperature (also denoted as Dmax).

[0032] When any difference Dmax exceeds the set threshold, the system will judge that the heat treatment furnace is in an abnormal operating state. This judgment standard is based on the uniformity requirement of temperature distribution during heat treatment. In normal operation, the temperature distribution in the heat treatment furnace should be relatively uniform, and the deviation of the highest and lowest point temperatures from the average temperature should be within the allowable range. If the deviation is too large, it may mean that there is uneven temperature distribution in the furnace, heating element failure or other abnormal conditions.

[0033] The main function of the cycle adjustment module is to set and adjust the duration of the monitoring cycle. During the heat treatment process, especially during the constant temperature heat treatment of the steel pipe, the system performs statistical analysis on the temperature data of the steel pipe area every n monitoring cycles. These temperature data include the average temperature Ta, the difference between the highest point and the average temperature Dmax, and the difference between the lowest point and the average temperature Dmin. The module will count the proportions of these temperature data exceeding the preset threshold intervals K1, K2 and K3, respectively, to evaluate the stability and uniformity of the temperature.

[0034] Calculation of weighted moving average In order to more accurately reflect the temperature change trend, the cycle adjustment module will calculate the weighted moving average T0 of the last n monitoring cycles. The specific process is as follows: Get the average temperature sequence: The system first gets the average temperature XT of the last n monitoring cycles. These average temperatures reflect the temperature level of the steel pipe area in each monitoring cycle.

[0035] Weighting: In order to give more importance to recent temperature data, the system assigns a weight ω to each average temperature XT i These weights gradually increase in chronological order, that is, the temperature data closer to the current moment has a higher weight. This weighting method enables the system to more sensitively capture recent temperature trends.

[0036] Calculate the weighted moving average T0: The calculation formula of the weighted moving average T0 is as follows: ; Among them, XTi represents the i-th average temperature XT, and ωi represents the weight of the i-th average temperature XT.

[0037] In order to further optimize the monitoring cycle, the system uses the weighted moving average value T0 and the average temperature T a The inflection point graph is drawn sequentially. The inflection point graph visually shows the temperature change trend over time by connecting the average temperature points of each monitoring cycle. The system calculates the slope k of the line segment between each two adjacent points to evaluate the rate of temperature change. The calculation formula of the cycle adjustment coefficient C is as follows: ; Among them, ki represents the slope of the i-th line segment in the inflection point diagram, kmax represents the maximum value of the slope, kmin represents the minimum value of the slope, and c represents the compensation coefficient, which is used to prevent the adjustment coefficient from being 0 or meaningless; then the duration of the next n monitoring cycles is Tnew=T / C. In this way, the system can shorten the monitoring cycle when the temperature changes drastically to collect data more frequently; and extend the monitoring cycle when the temperature changes steadily, thereby optimizing resource utilization.

[0038] Through the above process, the cycle adjustment module can dynamically adjust the monitoring cycle according to the actual temperature changes during the heat treatment process. This method not only improves the monitoring efficiency, but also ensures that temperature anomalies can be captured in time at critical stages, thereby providing strong guarantees for the stability of the heat treatment process and product quality.

[0039] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0040] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0041] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0042] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0043] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0044] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0045] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0046] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0047] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0048] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An online monitoring system for the temperature of a heated object in a heat treatment furnace, characterized in that: include: Infrared imaging module, used to generate thermal imaging of the temperature field in the heat treatment furnace based on infrared temperature measurement technology; A steel pipe identification module is used to preprocess the thermal image, perform edge detection on the preprocessed thermal image, identify the boundary line between each steel pipe area and the surrounding area, and obtain the steel pipe area in the thermal image; The temperature analysis module is used to obtain the temperature data of the steel pipe area, the temperature data includes the average temperature, the highest point temperature and the lowest point temperature, and judge whether the heat treatment of the steel pipe is running normally according to the temperature data; The cycle adjustment module is used to set the monitoring cycle, the standard duration of the monitoring cycle is T, the temperature data is counted every n monitoring cycles, the cycle adjustment coefficient is calculated based on the temperature data, and the duration of the next n monitoring cycles is calculated based on the cycle adjustment coefficient.

2. The online monitoring system for the temperature of a heated object in a heat treatment furnace according to claim 1, characterized in that: The process of generating a thermal imaging image of the temperature field in the heat treatment furnace by the infrared imaging module based on the infrared temperature measurement technology is as follows: The infrared imaging module is based on an infrared detector array composed of several infrared detectors. The infrared detector array receives infrared radiation energy in the heat treatment furnace, converts infrared radiation at different positions in the furnace into electrical signals, amplifies and filters the electrical signals through a built-in signal processing circuit, and converts analog-to-digital signals into digital signals. These digital signals are calculated based on a preset algorithm to obtain the temperature values ​​corresponding to each position in the heat treatment furnace, and generate a thermal imaging map of the temperature field in the heat treatment furnace through visualization processing.

3. The online monitoring system for the temperature of a heated object in a heat treatment furnace according to claim 1, characterized in that: The process of preprocessing the thermal image by the steel pipe recognition module is as follows: The thermal image is converted into a grayscale image. Based on the 3×3 template of the Laplace operator, each pixel in the grayscale image is multiplied and summed with the adjacent 3×3 pixels point by point. The summed grayscale value result is marked as the new grayscale value of the middle pixel, and all the pixels in the thermal image are updated respectively.

4. The online monitoring system for the temperature of a heated object in a heat treatment furnace according to claim 1, characterized in that: The steel pipe identification module performs edge detection on the preprocessed thermal image to identify the boundary line between each steel pipe area and the surrounding area as follows: Get the placement direction of the steel pipe, start from the edge of the grayscale image parallel to the steel pipe, select a column of pixels in turn, calculate the mean grayscale value of the selected column of pixels, and perform difference calculation with the mean grayscale value of the pixels in the next column. When the difference is greater than the preset threshold, mark the lower mean between the two columns of pixels as a pending boundary line and define it as the starting line. Traverse the grayscale image and mark the last pending boundary line as the end line. When the number of pending boundary lines is greater than 2, mark the pending boundary lines within the set range near the starting line as the starting line group. The pending boundary lines within the set range near the end line are marked as the end line group, and each pending boundary line in the start line group and the end line group is traversed respectively. For each pending boundary line, starting from one end of the pending boundary line, the grayscale value of the pixel point is compared with the grayscale value of the next pixel point in turn, and the smaller pixel point between the two pixel points whose difference is greater than the preset threshold is marked as an edge point, and all edge points in the start line group and the end line group are connected respectively, and the connected edge points are linearly fitted, and the fitted straight line is marked as the boundary line of the steel pipe area.

5. The online monitoring system for the temperature of a heated object in a heat treatment furnace according to claim 4, characterized in that: When the number of pending boundary lines is equal to 2, it is directly marked as the steel pipe area boundary line.

6. The online monitoring system for the temperature of a heated object in a heat treatment furnace according to claim 4, characterized in that: When the deviation between the slope of any fitted straight line and the slope of the set direction is greater than the set deviation, an abnormal prompt is issued.

7. The online monitoring system for the temperature of a heated object in a heat treatment furnace according to claim 1, characterized in that: The process of judging whether the heat treatment of the steel pipe is operating normally according to the temperature data in the temperature analysis module is as follows: The difference Dmax and the difference Dmax between the highest point temperature and the lowest point temperature and the average temperature are calculated respectively. When any difference is greater than the set difference, it is judged that the heat treatment furnace is operating abnormally.

8. The online monitoring system for the temperature of a heated object in a heat treatment furnace according to claim 1, characterized in that: The cycle adjustment module collects the temperature data every n monitoring cycles, calculates the cycle adjustment coefficient according to the temperature data, and calculates the duration of the next n monitoring cycles according to the cycle adjustment coefficient as follows: During the constant temperature heat treatment of the steel pipe, the average temperature Ta, difference Dmax, and difference Dmax of the steel pipe area are counted every n monitoring cycles, and the proportions K1, K2, and K3 of the average temperature Ta, difference Dmax, and difference Dmax exceeding the corresponding set interval are counted respectively; The weighted moving average value T0 of n monitoring cycles is statistically calculated, and T0 is added to the average temperature Ta sequence. A point diagram of the average temperature changing with the number of monitoring times is drawn according to the average temperature Ta sequence, and the slope k of the line segment between every two adjacent points is obtained. The calculation formula of the cycle adjustment coefficient C is: ； Among them, ki represents the slope of the i-th line segment in the inflection point graph, kmax represents the maximum value of the slope, kmin represents the minimum value of the slope, and c represents the compensation coefficient, which is used to prevent the adjustment coefficient value from being 0 or meaningless; Then the duration of the next n monitoring cycles is Tnew=T / C.

9. The online monitoring system for the temperature of a heated object in a heat treatment furnace according to claim 8, characterized in that: The specific process of the weighted moving average T0 of n monitoring periods is statistically as follows: Get the average temperature XT of the last n monitoring cycles, and assign a corresponding weight to each average temperature XT. The weight increases gradually according to the time sequence. The calculation formula of the weighted moving average value T0 is: ； Among them, XTi represents the i-th average temperature XT, and ωi represents the weight of the i-th average temperature XT.

Images